Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1992 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1244094 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1326080 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8929. Min Act: -0.0000

Data Index: 803482 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1189453 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8366. Min Act: -0.0000

Data Index: 260978 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1098353 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.9064. Min Act: -0.0000

Data Index: 911328 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1222609 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.6002. Min Act: -0.0000

Data Index: 308360 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.5394. Min Act: -0.0000

Data Index: 838218 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1035591 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.3970. Min Act: -0.0000

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.4184. Min Act: -0.0000

Data Index: 868433 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.4226. Min Act: -0.0000

Data Index: 499583 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.4015. Min Act: -0.0000

Data Index: 893434 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.3766. Min Act: -0.0000

Data Index: 630809 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1092453 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.3568. Min Act: -0.0000

Data Index: 97881 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.3285. Min Act: -0.0000

Data Index: 59123 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.9864. Min Range: -0.9864

Max Act: 0.3238. Min Act: -0.0000

Data Index: 350025 (C4 (Web Text))

Max Activating Token Index: 870